Video Generation

Today's Stories

1. 1

   Apple releases VideoFlexTok video tokenizer research

   Apple researchers published VideoFlexTok, a new approach to video tokenization that uses a coarse-to-fine method. The technique compresses video into a flexible-length token representation, rather than the standard spatiotemporal 3D grid approach that treats all video content equally. Traditional video tokenizers force downstream models—like text-to-video generators—to predict all low-level pixel details regardless of the video's complexity. VideoFlexTok's flexible approach may allow models to allocate computational resources more efficiently by adapting token density to the content, potentially reducing wasted processing on simple scenes.

   The research is available at machinelearning.apple.com/research/videoflextok, where practitioners can evaluate the method's performance gains against existing tokenization standards.

2. 2

   AI Music Video Generation: 10 Tools That Automate Your Creative Workflow in 2026

   AI Music Video Generation: 10 Tools That Automate Your Creative Workflow in 2026

3. 3

   Google launches Nano Banana 2 Lite and Gemini Omni Flash for faster AI images and video

   Google released two new AI models—Nano Banana 2 Lite for fast image generation at $0.034 per image in four seconds, and Gemini Omni Flash for video generation and editing via API at $0.10 per second of output. Both are now available to developers through the Gemini API and Google AI Studio. Nano Banana 2 Lite replaces Google's older image model and offers a lower-cost, faster option for developers who prioritize speed over quality. Gemini Omni Flash opens video generation to the API for the first time, allowing developers to combine text, images, and video in a single workflow—and Google recommends chaining both models together to quickly generate images and animate them into video.

   Gemini Omni Flash currently generates only ten-second clips, and audio references and scene extensions are not yet supported in the API. Character consistency across scene changes remains limited. Both models apply SynthID watermarks to tag AI-generated content, with verification available through the Gemini app, Gemini in Chrome, and Google Search.

4. 4

   Google rolls out Gemini Omni Flash API for enterprise video editing via conversation

   Google is now making Gemini Omni Flash, the first model in its new Omni family, available to developers and enterprise customers through an API. The model debuted to consumers at I/O 2026 in May. The key capability is the ability to edit a finished video clip through conversation, rather than just generating video from text prompts. Creating training videos or product explainers has traditionally required careful planning, a film crew or outside vendor, shooting, editing, and multiple revision rounds—making the cost and timeline prohibitive for many internal video projects. By allowing enterprises to edit finished clips through conversation, Google is aiming to simplify and accelerate the video production workflow, potentially making it more accessible for businesses that currently skip video due to complexity and resource constraints.

   The API rollout to developers and enterprise customers represents the first programmatic access to Omni—a step beyond the consumer and prosumer version that launched in May without a programmatic interface. This availability through an API is what makes the model usable for enterprise workflows at scale.

5. 5

   Soracom Adds New Feature to Wisora: Handover Function for AI and Human Collaborative Response

   Soracom Adds New Feature to Wisora: Handover Function for AI and Human Collaborative Response

6. 6

   Google DeepMind invests $75M in A24, signaling shift from video tools to content

   Google DeepMind invested $75 million（約120億円） in indie film studio A24 this week, with the two companies partnering to develop AI tools for filmmakers. Investment in AI video and media tech startups has more than tripled over the past five years, reaching $5.6 billion（約9000億円） this year, up over 43% from 2025's annual total. The market is shifting beyond competition over video-generation technology itself. Video generation is becoming easier to build, with new models from China rivaling US and European products, and incumbents developing their own AI capabilities. This means the real value may now lie in content creation and end products, not just the software layer—a change that opens opportunities for creative studios alongside tech companies.

   VCs are beginning to fund AI-native or AI-powered studios. Promise has raised funding from backers including Andreessen Horowitz and Google's AI Futures Fund, and London-based Wonder raised $12 million（約19億円） from investors including Atomico and LocalGlobe.